Search for Articles
International Journal of Clinical Medicine and Bioengineering
ISSN:2737-534X

Journal Browser

Vol.1, Iss.1, December 2021


 
 IJCMB 2021/12
Vol.1, Iss.1 : 12-24
https://doi.org/10.35745/ijcmb2021v01.01.0003
A Cortical Learning Machine for Learning Real-Valued and Ranked Data

James Ting-Ho Lo1* and Bryce Mackey-Williams Carey2
1Department of Mathematics and Statistics, University of Maryland Baltimore County, USA
2Amazon Web Services, Amazon.com, USA


Abstract:
The cortical learning machine (CLM) introduced in [1-3] is a low-order computational model of the neocortex. It has the real-time, photogragraphic, unsupervised, and hierarchical learning capabilities, which existing learning machines such as the multilayer perceptron and convolutional neural network do not have. The CLM is a network of processing units (PUs) each comprising novel computational models of dendrites (for encoding), synapses (for storing code covariance matrices), spiking/nonspiking somas (for evaluating empirical probabilities and generating spikes), and unsupervised/supervised Hebbian learning schemes. In this paper, the masking matrix in the CLM in [1-3] is generalized to enable the CLM to learn ranked and real-valued data in the form of the binary numbers and unary (thermometer) codes. The general masking matrix assigns weights to the bits in the binary and unary code to reflect their relative significances. Numerical examples are provided to illustrate that a single PU with the general masking matrix is a pattern recognizer with an efficacy comparable to those of leading statistical and machine learning methods, showing the potential of CLMs with multiple PUs especially in consideration of the aforementioned capabilities of the CLM.

Keywords:  Real-Time Learning, Photographic Learning, Real-Valued, Ranked, Masking Matrix, Neocortex, Pattern Recognition, Associative Memory, Unsupervised Learning, Hierarchical Learning

*Corresponding author; e-mail: jameslo@umbc.edu
© 2021   , ISSN 2737-534X




Back